diff --git a/docs/openapi.json b/docs/openapi.json
index 0b5b3ae3..80fa5b3d 100644
--- a/docs/openapi.json
+++ b/docs/openapi.json
@@ -2183,4 +2183,4 @@
       "description": "Hugging Face Text Generation Inference API"
     }
   ]
-}
+}
\ No newline at end of file
diff --git a/docs/source/supported_models.md b/docs/source/supported_models.md
index 832f88ef..3fa78ee9 100644
--- a/docs/source/supported_models.md
+++ b/docs/source/supported_models.md
@@ -20,6 +20,7 @@ Text Generation Inference enables serving optimized models on specific hardware
 - [Mixtral](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1)
 - [Gpt Bigcode](https://huggingface.co/bigcode/gpt_bigcode-santacoder)
 - [Phi](https://huggingface.co/microsoft/phi-1_5)
+- [PhiMoe](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct)
 - [Baichuan](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat)
 - [Falcon](https://huggingface.co/tiiuae/falcon-7b-instruct)
 - [StarCoder 2](https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1)
diff --git a/integration-tests/models/test_flash_phi35_moe.py b/integration-tests/models/test_flash_phi35_moe.py
index e3a9eff3..177c7f24 100644
--- a/integration-tests/models/test_flash_phi35_moe.py
+++ b/integration-tests/models/test_flash_phi35_moe.py
@@ -4,9 +4,7 @@ import pytest
 @pytest.fixture(scope="module")
 def flash_llama_chat_handle(launcher):
     with launcher(
-        "microsoft/Phi-3.5-MoE-instruct", 
-        num_shard=4,
-        cuda_graphs=[1, 2]
+        "microsoft/Phi-3.5-MoE-instruct", num_shard=4, cuda_graphs=[1, 2]
     ) as handle:
         yield handle